nansen-web-fetcher
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
nansen-clipackage from the npm registry. This package provides the command-line utility for web fetching. - [COMMAND_EXECUTION]: The skill executes the
nansenCLI tool through the Bash shell to retrieve content from external URLs. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes content from arbitrary external URLs and passes it directly to an LLM.
- Ingestion points: External URL content fetched via the
nansen web fetchcommand in SKILL.md. - Boundary markers: The skill does not implement delimiters or 'ignore' instructions to separate fetched content from user prompts.
- Capability inventory: Uses the
Bash(nansen:*)tool to perform network and processing tasks. - Sanitization: No validation or sanitization is performed on the retrieved web content before it is analyzed by the AI.
Audit Metadata